Triple
T5425129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abbey Bartlet |
E121344
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Abigail |
E29086
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Abigail | Statement: [Abbey Bartlet, givenName, Abigail]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abigail Context triple: [Abbey Bartlet, givenName, Abigail]
-
A.
Abigail
chosen
Abigail is a feminine given name of Hebrew origin meaning "my father is joy," historically popular in English-speaking countries.
-
B.
Abigail
Abigail is a fictional character portrayed by Idara Victor, best known from the television series "Rizzoli & Isles."
-
C.
Abigail Ruck
Abigail Ruck was the wife of Benning Wentworth, the long-serving colonial governor of New Hampshire in the 18th century.
-
D.
Abigail Cruttenden
Abigail Cruttenden is an English actress known for her work in film, television, and theatre, including roles in period dramas and British TV series.
-
E.
Hannah Franklin
Hannah Franklin was one of the lesser-known children in the large Franklin family that included American statesman and inventor Benjamin Franklin.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69bd463b58d88190b258261573de9e91 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd88142b4c8190a0a9fce117aaef14 |
completed | March 20, 2026, 5:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf3abbd1e481909ffb443812a9485a |
completed | March 22, 2026, 12:41 a.m. |
Created at: March 20, 2026, 2:06 p.m.